番茄收获机器人视觉定位中多光谱图像融合方法的研究
|
摘要
针对目前农业收获机器人视觉方面存在的难题,特别是果实采摘前的识别定位,普遍存在受环境干扰较大以及识别精度不高的难题,本文从两个可见光和一个近红外的三目视觉角度出发,利用多光谱图像融合的方式来寻求更好的解决方式,为后继果实的定位打下坚实的基础。开展的主要研究内容如下:
1)多光谱图像配准。图像融合的前提是图像的精确配准,因此本文对图像的配准进行了着重研究。对采集的多光谱图像进行了分析,采用Harris角点检测算子提取可见光图像和近红外图像角点特征,并对基于角点支持强度的角点匹配算法进行了改进,形成了番茄多光谱图像良好的角点匹配算法。之后对图像采用基于仿射变换的图像粗配准,并在彩色图像分割的前提下,提取可见光图像和近红外图像的收获目标及其邻域。再对提取得到的果实邻域利用Harris算子检测角点,并进行角点匹配,最后利用仿射变换实现了可见光图像和近红外图像中目标的精确配准。
2)多光谱图像融合。继图像精确配准之后,对多光谱图像融合进行了研究。本文对现有的融合算法——IHS变换法、主成分变换法和小波变换法进行了对比试验,通过主观和客观的基于熵、清晰度和标准差等几个方面进行了评价。主观方面,小波变换融合后的图像,具有果实和背景差异明显的特性,给后续的果实分割打下了良好的基础。客观方面,小波融合算法作用的图像具有较大的熵、清晰度和标准差,而且在实时性方面能够满足采摘机器人的要求,因此本研究最终选用小波变换融合来实现本研究多光谱图像的融合。
3)融合图像的分割与分析。融合前,对可见光图像采用了基于色差和受控分水岭的图像分割算法进行图像分割,图像融合之后,为了更加直观地显示融合前后图像的优劣和差异,依然采用前面分割算法对融合后的图像进行分割。并在分割之后对分割的质量进行了分析和讨论。结果表明,经过融合后的图像比融合前的图像在分割效果上有很高的成功率,说明本文的多光谱图像融合的研究达到了预期的目的,具有较好的实用性。
通过研究,在多光谱图像配准和融合方面取得了较大进展。系统能够对存在不同的遮挡情况下的果实进行有效的识别和分割,即使果实的成熟度不够,通过图像的融合也能够准确识别。本研究对提高我国农业收获机器人视觉识别技术水平具有一定的学术意义和实践价值。
Aiming at problems of agriculture harvest robot vision at present time, especially the problems of more sensitive to environment and low-precision in recognition and orientation before fruit picking, the paper uses three-eye vision technology of two visible and a NIR and imposes multi-spectral image fusion to seek well solving method to make stable groundwork for the following fruit orientation. The research is summarized as following:
1) Multi-spectral image registration. Considering the precondition of image fusion is precise image registration, the paper puts more emphasis on image registration. multi-spectral images that we captured are analyzed first. The paper detects corners of Visible image and NIR image using Harris corner detector and improves the corner matching method based on corner sustaining intensity, forming good corner matching method for multi-spectral image of tomato. Then, we coarsely register images basing on affine transform, and pick-up objects and its neighbor region(subimage) from images with color image segmentation as the premise. Then we detect corners of the subimages using Harris detector and match them. Finally we use affine transform to achieve precise registration of objects in Visible image and NIR image.
2) Multi-spectral image fusion. After the precisely registration, the paper does some research on multi-spectral image fusion. The paper compares three existing fusion method—IHS transform, PCA transform and wavelet transform methods to test multi-spectral images. The paper chose the wavelet transform method as the final fusion measure via subjective judgment and objective judge method—entropy, cross-entropy, standard deviation and definition. Subjectivly, Images using the wavelet transform method can make much difference between fruit and its background which is in favor of the segmentation of objects. Objectivity, Images using the wavelet transform method get more entropy, standard deviation and definition, and it can meet demand of real time, so, we chose the wavelet transform method to carry out the fusion of Multi-spectral images.
3. Segmentation and analysis of fused images. Befor the fusion,the paper introduces a segmentation arithmetic based on color difference and controlled watershed to segment fused image for the sementation of the visible image, and then, in order to show the differences between former and later segmentation of images more distinctness,we still use this segmenting method to segment fused images. And we analysis and discuss the quality of the segmentation. It come true that the segmentation of the images using fuse method has more succeed rate than images without using fuse method, so we consider that our Multi-spectral image fusion achieves the prospective aim and holds well practicability.
Our research has made great progress in multi-spectral image registration and fusion. The experimental system can effectively recognize and segment objects from different shelter conditions. Image fusion can distinguish tomatoes from fusional images even though they are not enough mature. The research is meaningful to improve the international competition in our agriculture field.
1)多光谱图像配准。图像融合的前提是图像的精确配准,因此本文对图像的配准进行了着重研究。对采集的多光谱图像进行了分析,采用Harris角点检测算子提取可见光图像和近红外图像角点特征,并对基于角点支持强度的角点匹配算法进行了改进,形成了番茄多光谱图像良好的角点匹配算法。之后对图像采用基于仿射变换的图像粗配准,并在彩色图像分割的前提下,提取可见光图像和近红外图像的收获目标及其邻域。再对提取得到的果实邻域利用Harris算子检测角点,并进行角点匹配,最后利用仿射变换实现了可见光图像和近红外图像中目标的精确配准。
2)多光谱图像融合。继图像精确配准之后,对多光谱图像融合进行了研究。本文对现有的融合算法——IHS变换法、主成分变换法和小波变换法进行了对比试验,通过主观和客观的基于熵、清晰度和标准差等几个方面进行了评价。主观方面,小波变换融合后的图像,具有果实和背景差异明显的特性,给后续的果实分割打下了良好的基础。客观方面,小波融合算法作用的图像具有较大的熵、清晰度和标准差,而且在实时性方面能够满足采摘机器人的要求,因此本研究最终选用小波变换融合来实现本研究多光谱图像的融合。
3)融合图像的分割与分析。融合前,对可见光图像采用了基于色差和受控分水岭的图像分割算法进行图像分割,图像融合之后,为了更加直观地显示融合前后图像的优劣和差异,依然采用前面分割算法对融合后的图像进行分割。并在分割之后对分割的质量进行了分析和讨论。结果表明,经过融合后的图像比融合前的图像在分割效果上有很高的成功率,说明本文的多光谱图像融合的研究达到了预期的目的,具有较好的实用性。
通过研究,在多光谱图像配准和融合方面取得了较大进展。系统能够对存在不同的遮挡情况下的果实进行有效的识别和分割,即使果实的成熟度不够,通过图像的融合也能够准确识别。本研究对提高我国农业收获机器人视觉识别技术水平具有一定的学术意义和实践价值。
Aiming at problems of agriculture harvest robot vision at present time, especially the problems of more sensitive to environment and low-precision in recognition and orientation before fruit picking, the paper uses three-eye vision technology of two visible and a NIR and imposes multi-spectral image fusion to seek well solving method to make stable groundwork for the following fruit orientation. The research is summarized as following:
1) Multi-spectral image registration. Considering the precondition of image fusion is precise image registration, the paper puts more emphasis on image registration. multi-spectral images that we captured are analyzed first. The paper detects corners of Visible image and NIR image using Harris corner detector and improves the corner matching method based on corner sustaining intensity, forming good corner matching method for multi-spectral image of tomato. Then, we coarsely register images basing on affine transform, and pick-up objects and its neighbor region(subimage) from images with color image segmentation as the premise. Then we detect corners of the subimages using Harris detector and match them. Finally we use affine transform to achieve precise registration of objects in Visible image and NIR image.
2) Multi-spectral image fusion. After the precisely registration, the paper does some research on multi-spectral image fusion. The paper compares three existing fusion method—IHS transform, PCA transform and wavelet transform methods to test multi-spectral images. The paper chose the wavelet transform method as the final fusion measure via subjective judgment and objective judge method—entropy, cross-entropy, standard deviation and definition. Subjectivly, Images using the wavelet transform method can make much difference between fruit and its background which is in favor of the segmentation of objects. Objectivity, Images using the wavelet transform method get more entropy, standard deviation and definition, and it can meet demand of real time, so, we chose the wavelet transform method to carry out the fusion of Multi-spectral images.
3. Segmentation and analysis of fused images. Befor the fusion,the paper introduces a segmentation arithmetic based on color difference and controlled watershed to segment fused image for the sementation of the visible image, and then, in order to show the differences between former and later segmentation of images more distinctness,we still use this segmenting method to segment fused images. And we analysis and discuss the quality of the segmentation. It come true that the segmentation of the images using fuse method has more succeed rate than images without using fuse method, so we consider that our Multi-spectral image fusion achieves the prospective aim and holds well practicability.
Our research has made great progress in multi-spectral image registration and fusion. The experimental system can effectively recognize and segment objects from different shelter conditions. Image fusion can distinguish tomatoes from fusional images even though they are not enough mature. The research is meaningful to improve the international competition in our agriculture field.
引文
[1]Schertz C.E,Brown G.K.Basic considerations in mechanizing citrus harvest [J].Transactions of the ASAE,1968,11(2):343-346
[2]Parrish E.,and A.K.Goksel.1977.Pictorial pattern recognition applied to fruit harvesting.Transactions of the ASAE,1977,20(5):822-827
[3]D'Esnon A G,Rabatel G,Pellenc R.A self-propelled robot to pick apples[J].Transactions of the ASAE,987,7:1032-1037
[4]Rabatel G.,1988.A vision system for magali,the fruit picking robot[C].Agricultural Engineering,Paris,London,U.K.Paper 88293,AGENG88,Int,Conf.Ministry of Agriculture,Fisheries and Food 1988
[5]Kassay L.Hungarian robotic apple harvesten[C].ASAE Paper No.92-7042,1-14.St.Joseph.Mich.:ASAE.1992
[6]Buemi F.,M.Massa,and G.Sandini,1995.Agrobot:A robotic system for greenhouse operations.In 4th Workshop on Robotics in Agriculture,IARP,Tolouse,172-184
[7]S.Limsiroratana,Y.Lkeda,2002.On image analysis for harvesting tropical fruits.SICE02-0824:1336-1341
[8]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Meuleman J,Bontsema J,Van Os EA.Field Test of an Autonomous Cucumber Picking Robot[J].Biosystems Engineering,2003,86(3):305-313
[9]杨秀坤,陈晓光等.水果表面缺陷自动检测系统中的人工智能方法研究[J].农业工程学报,1997,13(增刊):242-247
[10]滕召胜,蔡铁,王可宁等.一种智能化粮情自动检测系统[J].农业工程学报,2001,17(4):144-157
[11]蔡健荣,赵杰文.自然场景下的成熟苹果计算机视觉识别[J].农业机械学报,2005,36(2):61-64
[12]吕俊伟,马成林等.采用多光谱图像融合提高作物和杂草灰度比值[J].农业工程学报,2005,21(11):99-102
[13]尹建军.基丁颜色差异的果实自动识别方法与双目定位技术研究[D].江苏大学,2006
[14]尹建军,毛罕平等.不同生长状态下多目标番茄图像的自动分割方法[J].农业工程学报,2006,22(10):149-152
[15]贾渊,姬长英.农产品自动检测中的常见颜色模型[J].农机化研究,2004,4:205-208、213
[16]应义斌,付峰.水果品质机器视觉检测中的图像颜色变换模型[J].农业机械学报,2004,35(1):85-89
[17]周水琴,应义斌.颜色模型在农产品颜色检测与分级中的应用[J].浙江大学学报(农业与生命科学版),2003,29(6):684-688
[18]方如明,蔡健荣等编著.计算机图像处理技术及其在农业工程中的应用[M].北京:清华大学出版社,1999.
[19]章孝灿等编著.遥感数字图像处理[M].杭州:浙江大学出版社,1997
[20]李庆中,汪懋平.农业生物模式识别中的计算机视觉技术[J].中国图象图形学报,2004,4(7):610-616
[21]Naoshi Kondo,Ting KC.Robotics for bio2production systems.SAE,998
[22]林伟明,毛罕平等.多光谱视觉技术在收获机器人中的应用[J].农业装备技术,2004,30(6):15-18
[23]Rafael C.Gonzalez,Richard E.Woods.阮秋琦,阮宇智等译.数字图像处理(第二版)[M].北京:电子工业出版社,2003
[24]王家文,李仰军等编著.MATLAB7.0图形图像处理[M].北京:国防工业出版社,2005:221-222
[25]徐飞,施晓红等编著.MATLAB应用图像处理[M].西安:西安电子科技大学出版社,2002:149-151
[26]孔渊,崔洪洲等.多光谱图像配准实时处理技术研究[J].红外技术,2004,26(4):41-44
[27]王红梅,张科等.图像匹配研究进展[J].计算机工程与应用,2004,19:42-45
[28]曾文锋,王志怀等.基于小波变换的红外图像配准方法[J].激光与红外,2003,33(4):288-289
[29]伍君,李树涛等.基于小波分解和互信息测度的图像配准方法[J].计算机工程与应用,2005,73-75
[30]倪东,鲍旭东等.基于互信息的多光谱图像配准[J].山东生物医学工程,2003,1:8-12
[31]李卫华,周军等.一种基于互信息和小波分解的图像配准算法[J].计算机工程与应用,2005,33:31-34
[32]伍军,李树涛.基于小波分解和互信息测度的图像配准方法[J].计算机工程与应用,2005,5:73-75
[33]Kuglin C D,Hines D C.The phase correlation image alignment method[A].Proc IEEE 1975 Int Conf Cyber2netics and Society[C].1975,163-165
[34]Lee D J,Krile T F,Mitra S.Digital registration techniques for sequential fundus images[A].IEEE Proc of SPIE:Applications of Digital Image Processing X 829[C].1987,293-300
[35]刘卫光,崔江涛等.插值和相位相关的图像亚象素配准方法[J].计算机辅助设计与图形学学报,2005,17(6):1273-1277
[36]曾文锋,王志怀等.基于小波变换的红外图像配准方法[J].激光与红外,2003,33(4):288-289
[37]王跃,毛士艺等.一种应用Partial Hausdorff距离的多尺度图像配准方法[J].航空学报,2004,25(6):593-597
[38]曾文锋.红外与可见光图像融合中的快速配准方法[J].红外与激光工程,2002,31(2):158-160
[39]席志红,刘利彬等.SUSAN角点检测算法改进[J].应用科技,2006,33(9):29-32
[40]Rohr K.Localization properties of direct corner detectors.Journal of Mathematical Imaging and Vision,1994,4(2):139-150
[41]WangMao2jun,WuWen2yen,HuangL iang2kai,et al.Comer detection using bending value[J].Pattern Recognition Letters,1995,16:575-583
[42]Quddus A,Fahmy M M.An improved wavelet-based comer detection technique [J].Acoustics,Speech and Signal Processing,1999.Proceedings of IEEE International Conference on,1999,6:3213-3216
[43]Mokhtarian F,Suomela R.Robust image comer detection through curvature scale space [J].IEEE Transactions on Pattern Analysis andMachine Intelligence,1998,20(12):1376-1381
[44]田原,梁德群等.直接基于灰度图像的多尺度角点检测方法[J].信号处理,1998,14:6-11
[45]Zitova B,Kautsky J,Peters G.Robust detection of significant points in multiframe images[J].Pattern Recongnition Letters,1999,20:199-206
[46]Smith SM,Brady J M.SUSAN—a new app roach to low level image p rocessing[J].International Journal of ComputerVision,1997,23(1):45-278
[47]文杨天,李征等.基于SUSAN算法的图像配准[J].计算机应用,2006,26(10):2380-2382.
[48]Mokhtarian F,Suomela R.Curvature scale space for robust image corner detection[A].In:Proc.Of Fourteenth Intl.Conf.on Pattern Recognition.vol 2,16-20,1998,1819-1821
[49]Otrite C.Lopez JE,Aleolea A.Curve segmentation by continuous smoothing at multiple scales.In;Proc.of Intl.Conf.on Image Processing.vol 3,16-19,1996,579-582
[50]Kwanghoon S,Kim J H,Alexander W E.A mean field anealing approach to robust corner detection[J].IEEE Transaction on Systems,Man and Cybernetics.Part B.1998,28(1):82-90
[51]ZUN IGA OA,HARAL ICK R.Comer detection using the facetrnodel[A].In Proceedings of CVPRp83[C].Arlington,VA,USA,June1983,30-37
[52]SMITH SM,BRADY JM.SUSAN2a new app roach to low level image processing[J].Journal of ComputerVision,1997,23(1):45-78
[53]MED ION I G,YASUMOTO Y.comer detection and curve representation using cubic B-Sp line[J].Computer Vision,Graphics,Image Process,1987,39(3):267-278
[54]彭晓明,张启衡.一种基于小波变换的角点提取方法[J].光电工程,2000,27(1):48-51
[55]Lee Jiann-shu,et al.Multiscale comer detection by using wavelet transform[J].IEEE Trans Image Processing,1995,4(1):100-104
[56]Harris C and StephensM.A combined corner and edge detector.Proceedings of the 4th Alvey Vision Conference,1988:147-151
[57]Smith SM,BRADYM.SUSAN2a new app roach to low level image processing[J].International Journal of Computer.1997,23(1):45-78
[58]刘博,仲思东.一种基于自适应阈值的SUSAN角点提取方法[J].红外技术,2006,28(6):331-333
[59]董瑞,梁栋等.基于颜色和几何特征的图像特征点匹配算法[J].计算机技术与发 展,2006,16(12):16-18
[60]Scot G L,Longuet—Higgins H C.An algorithm for associating the features of two patterns[C]// Proe Royal Society.London:[s.l.],1991:21-26
[61]胡明吴,任明武等.一种快速实用的特征点匹配算法[J].计算机工程,2004,30(9):31-33
[62]周骥,石教英等.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报,2002,14(8):754-758
[63]张继贤,李国胜等.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77
[64]曹闻,李弼程等.一种基于小波变换的图像配准方法[J].测绘通报,2004,2:16-19
[65]张迁,刘政凯等.基于SUSAN算法的航空影响的自动配准[J].测绘学报,2003,32(2):245-250
[66]陶冰洁,王敬儒等.采用仿射变换的红外与可见光图像配准方法[J].光电工程,2004,31(11):39-41
[67]Garguet—Duport B,Girel J,Chassery J M,et al.The use of multiresolution analysis and wavelets transform for merging SPOT panchromatic and multispectral image data[J].Photogrammetric Engineering& Remote Sensing,1996,62(9):1057-1066
[68]Pat S Chavez.Comparison of three different methods to merge multiresolution and muhispectral data:Landsat TM and SPOT panchromatic[J].Photogrammetric Engineering& Remote Sensing,1991,57(3):259-303
[69]F.Tupin,M.Roux.Detection of building outlines based on the fusion of SAR and optical features[J].ISPRS Journal of Photogrammetry&Remote Sensing 58(2003)71-82
[70]吕俊伟,马成林等.采用多光谱图像融合提高作物和杂草灰度比值[J].农业工程学报,2005,21(11):99-102
[71]钱永兰,杨邦杰等.用基于IHS变换的SPOT—5遥感图像融合进行作物识别[J].农业工程学报,2005,21(1):102-105
[72]刘哲,郝重阳等.多光谱图像与全色图像的象素级融合研究[J].数据采集与处理,2003,18(3):296-301
[73]潘震中.多传感器信息融合技术的研究[J].无线通信技术,1994,20(2):67-74
[74]张微,毛启明等.不同高分辨率遥感图像融合技术特征比较[J].东海海洋2005,23(1):23-31
[75]陈勇,皮德富等.基于小波变换的红外图像融合技术研究[J].红外与激光工程,2001,30(1):15-17
[76]李玲玲,周成平等.基于易操纵金字塔的多传感器图像融合[J].计算机工程与应用,2003.22:24-27
[77]马建文,赵忠明,布和敖斯尔.遥感数据模型与处理方法[M].北京:中国科学技术出版社,2001
[78]周前祥,敬忠良等.不同光谱与空间分辨率遥感图像融合方法的理论研究[J].遥感技术与应用,2003,18(1):41-46
[79]Harrison J R,Murray R,Hirose T.IHS transform for the integration of radar imagery with other remotely sensed data[J].PE & RS,1990,56(12):1631-1641
[80]Cast leman K R.Digital image processing[M].Newsey:P rent ice Hall Press,1996
[81]贾永红,李德仁等.四种IHS变换用于SAR与TM影像复合比较[J].遥感学报,1998,2(2):103-106
[82]ZHU Shu-long,ZHANG Zhan-mu.The acquisition and analysis of remote sensing image[M].Beijing:Science Press,2000
[83]Yesou H,Besnus Y,Polet Y.Extraction of spectral information from landsat TM data and merger with SPOT panchromatic imagery—A contribution to the study of Geological structures[J].ISPRS Journal of Photogrammetry and Remote Sensing,1993,48(5):23-26
[84]巫震宇,王鹏等.多传感器遥感图像数据融合研究[J].空间科学学报,2006,26(1):48-53
[85]付炜,邢广忠等.多分辨率遥感图像的特征小波变换融合模式研究[J].测控技术,2004,23:24-26
[86]吉书鹏,丁晓青.可见光与红外图像增强融合算法研究[J].红外与激光上程,2002,31(6):518-522
[87]Xue Jingtao,Zhang Yujin,Liu Xinggang.Threshold select ion using cross-entropy and fuzzy divergence[J].SPIE Electronic Imaging and Multimedia Systems,1998,3561:152-162
[88]陶冰洁,王敬儒等.基于小波系数相关性的图像融合新方法[J].激光与红外,2006,36(3):227-230
[89]陈少辉,张秋文等.基于归一化方差的多分辨率图像融合方法[J].计算机工程与应用,2005,3:25-27
[90]马恒,贾传荧等.基于空间频率的图像融合方法[J].计算机工程与应用,2005,31:215-218
[91]吴兆福,高飞等.基于边缘特征的遥感影像小波变换融合法[J].地球科学进展,2005,20(7):705-709
[92]李弼程,魏俊等.基于IHS变换与小波变换的遥感图像融合[J].数据采集与处理,2003,18(3):268-272
[93]韩玲,吴汉宁.象素级多源遥感影像信息融合的客观分析与质量评价[J].应用技术,2005,5:40-44
[94]夏明革,何友等.象素级图像融合方法与融合效果评价[J].遥感技术与应用,2002,17(4):224-229
[2]Parrish E.,and A.K.Goksel.1977.Pictorial pattern recognition applied to fruit harvesting.Transactions of the ASAE,1977,20(5):822-827
[3]D'Esnon A G,Rabatel G,Pellenc R.A self-propelled robot to pick apples[J].Transactions of the ASAE,987,7:1032-1037
[4]Rabatel G.,1988.A vision system for magali,the fruit picking robot[C].Agricultural Engineering,Paris,London,U.K.Paper 88293,AGENG88,Int,Conf.Ministry of Agriculture,Fisheries and Food 1988
[5]Kassay L.Hungarian robotic apple harvesten[C].ASAE Paper No.92-7042,1-14.St.Joseph.Mich.:ASAE.1992
[6]Buemi F.,M.Massa,and G.Sandini,1995.Agrobot:A robotic system for greenhouse operations.In 4th Workshop on Robotics in Agriculture,IARP,Tolouse,172-184
[7]S.Limsiroratana,Y.Lkeda,2002.On image analysis for harvesting tropical fruits.SICE02-0824:1336-1341
[8]Van Henten E J,Hemming J,Van Tuijl B A J,Kornet J G,Meuleman J,Bontsema J,Van Os EA.Field Test of an Autonomous Cucumber Picking Robot[J].Biosystems Engineering,2003,86(3):305-313
[9]杨秀坤,陈晓光等.水果表面缺陷自动检测系统中的人工智能方法研究[J].农业工程学报,1997,13(增刊):242-247
[10]滕召胜,蔡铁,王可宁等.一种智能化粮情自动检测系统[J].农业工程学报,2001,17(4):144-157
[11]蔡健荣,赵杰文.自然场景下的成熟苹果计算机视觉识别[J].农业机械学报,2005,36(2):61-64
[12]吕俊伟,马成林等.采用多光谱图像融合提高作物和杂草灰度比值[J].农业工程学报,2005,21(11):99-102
[13]尹建军.基丁颜色差异的果实自动识别方法与双目定位技术研究[D].江苏大学,2006
[14]尹建军,毛罕平等.不同生长状态下多目标番茄图像的自动分割方法[J].农业工程学报,2006,22(10):149-152
[15]贾渊,姬长英.农产品自动检测中的常见颜色模型[J].农机化研究,2004,4:205-208、213
[16]应义斌,付峰.水果品质机器视觉检测中的图像颜色变换模型[J].农业机械学报,2004,35(1):85-89
[17]周水琴,应义斌.颜色模型在农产品颜色检测与分级中的应用[J].浙江大学学报(农业与生命科学版),2003,29(6):684-688
[18]方如明,蔡健荣等编著.计算机图像处理技术及其在农业工程中的应用[M].北京:清华大学出版社,1999.
[19]章孝灿等编著.遥感数字图像处理[M].杭州:浙江大学出版社,1997
[20]李庆中,汪懋平.农业生物模式识别中的计算机视觉技术[J].中国图象图形学报,2004,4(7):610-616
[21]Naoshi Kondo,Ting KC.Robotics for bio2production systems.SAE,998
[22]林伟明,毛罕平等.多光谱视觉技术在收获机器人中的应用[J].农业装备技术,2004,30(6):15-18
[23]Rafael C.Gonzalez,Richard E.Woods.阮秋琦,阮宇智等译.数字图像处理(第二版)[M].北京:电子工业出版社,2003
[24]王家文,李仰军等编著.MATLAB7.0图形图像处理[M].北京:国防工业出版社,2005:221-222
[25]徐飞,施晓红等编著.MATLAB应用图像处理[M].西安:西安电子科技大学出版社,2002:149-151
[26]孔渊,崔洪洲等.多光谱图像配准实时处理技术研究[J].红外技术,2004,26(4):41-44
[27]王红梅,张科等.图像匹配研究进展[J].计算机工程与应用,2004,19:42-45
[28]曾文锋,王志怀等.基于小波变换的红外图像配准方法[J].激光与红外,2003,33(4):288-289
[29]伍君,李树涛等.基于小波分解和互信息测度的图像配准方法[J].计算机工程与应用,2005,73-75
[30]倪东,鲍旭东等.基于互信息的多光谱图像配准[J].山东生物医学工程,2003,1:8-12
[31]李卫华,周军等.一种基于互信息和小波分解的图像配准算法[J].计算机工程与应用,2005,33:31-34
[32]伍军,李树涛.基于小波分解和互信息测度的图像配准方法[J].计算机工程与应用,2005,5:73-75
[33]Kuglin C D,Hines D C.The phase correlation image alignment method[A].Proc IEEE 1975 Int Conf Cyber2netics and Society[C].1975,163-165
[34]Lee D J,Krile T F,Mitra S.Digital registration techniques for sequential fundus images[A].IEEE Proc of SPIE:Applications of Digital Image Processing X 829[C].1987,293-300
[35]刘卫光,崔江涛等.插值和相位相关的图像亚象素配准方法[J].计算机辅助设计与图形学学报,2005,17(6):1273-1277
[36]曾文锋,王志怀等.基于小波变换的红外图像配准方法[J].激光与红外,2003,33(4):288-289
[37]王跃,毛士艺等.一种应用Partial Hausdorff距离的多尺度图像配准方法[J].航空学报,2004,25(6):593-597
[38]曾文锋.红外与可见光图像融合中的快速配准方法[J].红外与激光工程,2002,31(2):158-160
[39]席志红,刘利彬等.SUSAN角点检测算法改进[J].应用科技,2006,33(9):29-32
[40]Rohr K.Localization properties of direct corner detectors.Journal of Mathematical Imaging and Vision,1994,4(2):139-150
[41]WangMao2jun,WuWen2yen,HuangL iang2kai,et al.Comer detection using bending value[J].Pattern Recognition Letters,1995,16:575-583
[42]Quddus A,Fahmy M M.An improved wavelet-based comer detection technique [J].Acoustics,Speech and Signal Processing,1999.Proceedings of IEEE International Conference on,1999,6:3213-3216
[43]Mokhtarian F,Suomela R.Robust image comer detection through curvature scale space [J].IEEE Transactions on Pattern Analysis andMachine Intelligence,1998,20(12):1376-1381
[44]田原,梁德群等.直接基于灰度图像的多尺度角点检测方法[J].信号处理,1998,14:6-11
[45]Zitova B,Kautsky J,Peters G.Robust detection of significant points in multiframe images[J].Pattern Recongnition Letters,1999,20:199-206
[46]Smith SM,Brady J M.SUSAN—a new app roach to low level image p rocessing[J].International Journal of ComputerVision,1997,23(1):45-278
[47]文杨天,李征等.基于SUSAN算法的图像配准[J].计算机应用,2006,26(10):2380-2382.
[48]Mokhtarian F,Suomela R.Curvature scale space for robust image corner detection[A].In:Proc.Of Fourteenth Intl.Conf.on Pattern Recognition.vol 2,16-20,1998,1819-1821
[49]Otrite C.Lopez JE,Aleolea A.Curve segmentation by continuous smoothing at multiple scales.In;Proc.of Intl.Conf.on Image Processing.vol 3,16-19,1996,579-582
[50]Kwanghoon S,Kim J H,Alexander W E.A mean field anealing approach to robust corner detection[J].IEEE Transaction on Systems,Man and Cybernetics.Part B.1998,28(1):82-90
[51]ZUN IGA OA,HARAL ICK R.Comer detection using the facetrnodel[A].In Proceedings of CVPRp83[C].Arlington,VA,USA,June1983,30-37
[52]SMITH SM,BRADY JM.SUSAN2a new app roach to low level image processing[J].Journal of ComputerVision,1997,23(1):45-78
[53]MED ION I G,YASUMOTO Y.comer detection and curve representation using cubic B-Sp line[J].Computer Vision,Graphics,Image Process,1987,39(3):267-278
[54]彭晓明,张启衡.一种基于小波变换的角点提取方法[J].光电工程,2000,27(1):48-51
[55]Lee Jiann-shu,et al.Multiscale comer detection by using wavelet transform[J].IEEE Trans Image Processing,1995,4(1):100-104
[56]Harris C and StephensM.A combined corner and edge detector.Proceedings of the 4th Alvey Vision Conference,1988:147-151
[57]Smith SM,BRADYM.SUSAN2a new app roach to low level image processing[J].International Journal of Computer.1997,23(1):45-78
[58]刘博,仲思东.一种基于自适应阈值的SUSAN角点提取方法[J].红外技术,2006,28(6):331-333
[59]董瑞,梁栋等.基于颜色和几何特征的图像特征点匹配算法[J].计算机技术与发 展,2006,16(12):16-18
[60]Scot G L,Longuet—Higgins H C.An algorithm for associating the features of two patterns[C]// Proe Royal Society.London:[s.l.],1991:21-26
[61]胡明吴,任明武等.一种快速实用的特征点匹配算法[J].计算机工程,2004,30(9):31-33
[62]周骥,石教英等.图像特征点匹配的强壮算法[J].计算机辅助设计与图形学学报,2002,14(8):754-758
[63]张继贤,李国胜等.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77
[64]曹闻,李弼程等.一种基于小波变换的图像配准方法[J].测绘通报,2004,2:16-19
[65]张迁,刘政凯等.基于SUSAN算法的航空影响的自动配准[J].测绘学报,2003,32(2):245-250
[66]陶冰洁,王敬儒等.采用仿射变换的红外与可见光图像配准方法[J].光电工程,2004,31(11):39-41
[67]Garguet—Duport B,Girel J,Chassery J M,et al.The use of multiresolution analysis and wavelets transform for merging SPOT panchromatic and multispectral image data[J].Photogrammetric Engineering& Remote Sensing,1996,62(9):1057-1066
[68]Pat S Chavez.Comparison of three different methods to merge multiresolution and muhispectral data:Landsat TM and SPOT panchromatic[J].Photogrammetric Engineering& Remote Sensing,1991,57(3):259-303
[69]F.Tupin,M.Roux.Detection of building outlines based on the fusion of SAR and optical features[J].ISPRS Journal of Photogrammetry&Remote Sensing 58(2003)71-82
[70]吕俊伟,马成林等.采用多光谱图像融合提高作物和杂草灰度比值[J].农业工程学报,2005,21(11):99-102
[71]钱永兰,杨邦杰等.用基于IHS变换的SPOT—5遥感图像融合进行作物识别[J].农业工程学报,2005,21(1):102-105
[72]刘哲,郝重阳等.多光谱图像与全色图像的象素级融合研究[J].数据采集与处理,2003,18(3):296-301
[73]潘震中.多传感器信息融合技术的研究[J].无线通信技术,1994,20(2):67-74
[74]张微,毛启明等.不同高分辨率遥感图像融合技术特征比较[J].东海海洋2005,23(1):23-31
[75]陈勇,皮德富等.基于小波变换的红外图像融合技术研究[J].红外与激光工程,2001,30(1):15-17
[76]李玲玲,周成平等.基于易操纵金字塔的多传感器图像融合[J].计算机工程与应用,2003.22:24-27
[77]马建文,赵忠明,布和敖斯尔.遥感数据模型与处理方法[M].北京:中国科学技术出版社,2001
[78]周前祥,敬忠良等.不同光谱与空间分辨率遥感图像融合方法的理论研究[J].遥感技术与应用,2003,18(1):41-46
[79]Harrison J R,Murray R,Hirose T.IHS transform for the integration of radar imagery with other remotely sensed data[J].PE & RS,1990,56(12):1631-1641
[80]Cast leman K R.Digital image processing[M].Newsey:P rent ice Hall Press,1996
[81]贾永红,李德仁等.四种IHS变换用于SAR与TM影像复合比较[J].遥感学报,1998,2(2):103-106
[82]ZHU Shu-long,ZHANG Zhan-mu.The acquisition and analysis of remote sensing image[M].Beijing:Science Press,2000
[83]Yesou H,Besnus Y,Polet Y.Extraction of spectral information from landsat TM data and merger with SPOT panchromatic imagery—A contribution to the study of Geological structures[J].ISPRS Journal of Photogrammetry and Remote Sensing,1993,48(5):23-26
[84]巫震宇,王鹏等.多传感器遥感图像数据融合研究[J].空间科学学报,2006,26(1):48-53
[85]付炜,邢广忠等.多分辨率遥感图像的特征小波变换融合模式研究[J].测控技术,2004,23:24-26
[86]吉书鹏,丁晓青.可见光与红外图像增强融合算法研究[J].红外与激光上程,2002,31(6):518-522
[87]Xue Jingtao,Zhang Yujin,Liu Xinggang.Threshold select ion using cross-entropy and fuzzy divergence[J].SPIE Electronic Imaging and Multimedia Systems,1998,3561:152-162
[88]陶冰洁,王敬儒等.基于小波系数相关性的图像融合新方法[J].激光与红外,2006,36(3):227-230
[89]陈少辉,张秋文等.基于归一化方差的多分辨率图像融合方法[J].计算机工程与应用,2005,3:25-27
[90]马恒,贾传荧等.基于空间频率的图像融合方法[J].计算机工程与应用,2005,31:215-218
[91]吴兆福,高飞等.基于边缘特征的遥感影像小波变换融合法[J].地球科学进展,2005,20(7):705-709
[92]李弼程,魏俊等.基于IHS变换与小波变换的遥感图像融合[J].数据采集与处理,2003,18(3):268-272
[93]韩玲,吴汉宁.象素级多源遥感影像信息融合的客观分析与质量评价[J].应用技术,2005,5:40-44
[94]夏明革,何友等.象素级图像融合方法与融合效果评价[J].遥感技术与应用,2002,17(4):224-229
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |